Research Agent

The green agent evaluates research and web agents on long-horizon, multi-step reasoning tasks constructed through counterfactual expansion to expose jagged intelligence and weakness as task complexity increases. Tasks span information seeking, financial analysis, and scientific investigation, and require agents to sustain coherent reasoning over extended web-based and code-based trajectories. For each task, the underlying reasoning chain is systematically expanded to increase difficulty in a controlled manner. This design enables precise diagnosis of when and how a research or web agent fails within a long-horizon task, rather than only measuring final-task success.

he agent performs a slide-by-slide comparison between Source Research and the Generated Slides. It looks for: Hallucinations: Does the slide claim something that isn't in the research? Retention: Did the slide forget the most important data points or key takeaways? Alignment: Do the visual elements (the "explicit description"), the speaker notes, and the research all tell the same story? Risk: Is there a risk that the slide is oversimplifying or misrepresenting complex data?

We propose a novel benchmark inspired by the MathWorks Math Modeling Challenge (https://m3challenge.siam.org), where a green agent defines real-world modeling problem contexts (e.g., housing markets, energy use, or population dynamics) and provides multiple relevant datasets. White agents operate under a fixed budget and must decide which subsets of these datasets to use, then construct mathematical models to forecast future trends. The green agent evaluates submissions by comparing generated forecasts against hidden ground-truth trends, measuring both accuracy and efficiency. Unlike existing benchmarks that focus on single-task accuracy, our benchmark emphasizes decision-making and context-aware reasoning: white agents must choose what data to incorporate and which modeling approach to use. Our contribution is a new environment that combines applied data science with resource-constrained modeling, offering a scalable way to evaluate agents on modeling under limited information.

Purple research agent built on Reflexive Agent Architecture. Handles academic literature review, news fact-checking, and technical troubleshooting using MCP tools. Supports dual-control environments (ResearchToolBench τ²-bench style). PRIME→EXECUTE→REFLECT cognitive loop.

Building effective RAG (Retrieval-Augmented Generation) systems requires careful selection and configuration of multiple interdependent components -- document converters, chunking strategies, embedding models, vector stores, and re-rankers. However, there is no standardized way to evaluate how different component combinations perform on domain-specific knowledge corpora. Our green agent provides an automated RAG evaluation benchmark that assesses participant agents across three key dimensions: 1) Retrieval Quality - ROUGE-L and BLEU scores measure how well retrieved content aligns with ground-truth answers 2) Response Coherence - Semantic coherence scoring evaluates answer quality independent of exact lexical matches 3) End-to-End Performance - Pass rate and latency metrics capture practical system effectiveness 4) Note: While our underlying agentic-rag SDK supports additional evaluation methods (METEOR, BERTScore, LLM-as-Judge), this benchmark focuses on these core metrics to provide fast, reproducible assessments. The benchmark enables researchers and practitioners to systematically experiment with pipeline configurations, comparing PDF vs. text converters, sentence-transformers vs. OpenAI embeddings, different chunk sizes, and various re-ranking strategies, to identify optimal component combinations for their specific knowledge domains. By standardizing RAG evaluation through the A2A protocol, our benchmark accelerates the discovery of best practices for building production-ready retrieval systems, reducing the trial-and-error typically required when deploying RAG applications on specialized corpora. Architecture: All pipeline configurations and computational results are persisted in a Neo4j knowledge graph, enabling participants to reuse intermediate computations (embeddings, chunked documents) across experiments. This graph-based approach provides full transparency into how documents flow through indexing and retrieval pipelines, making it easy to debug, iterate, and compare different RAG configurations. Current Benchmark Domain: The evaluation corpus consists of 100 peer-reviewed research papers on female reproductive longevity, paired with 15 expert-curated question-answer pairs designed to test both factual retrieval and reasoning across documents.